{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZLI4DH3QSXP6QEMZHFCYKP27IB","short_pith_number":"pith:ZLI4DH3Q","schema_version":"1.0","canonical_sha256":"cad1c19f7095dfe811993945853f5f4066b314943f2597af7efef818a6a20f1f","source":{"kind":"arxiv","id":"2403.08967","version":2},"attestation_state":"computed","paper":{"title":"PathM3: A Multimodal Multi-Task Multiple Instance Learning Framework for Whole Slide Image Classification and Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hehuan Ma, Junzhou Huang, Michael Xiao, Qifeng Zhou, Wenliang Zhong, Yuzhi Guo","submitted_at":"2024-03-13T21:19:12Z","abstract_excerpt":"In the field of computational histopathology, both whole slide images (WSIs) and diagnostic captions provide valuable insights for making diagnostic decisions. However, aligning WSIs with diagnostic captions presents a significant challenge. This difficulty arises from two main factors: 1) Gigapixel WSIs are unsuitable for direct input into deep learning models, and the redundancy and correlation among the patches demand more attention; and 2) Authentic WSI diagnostic captions are extremely limited, making it difficult to train an effective model. To overcome these obstacles, we present PathM3"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.08967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T21:19:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d73c57bc9178962c352554aad8acbe9e0e4a86f2acb4d8c2ec71ba099ae9a469","abstract_canon_sha256":"9b010e3cd7e8a909600ec3ccde97269add03af4fdf86fe9503eb9801486f408b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:42.175843Z","signature_b64":"/x9gZKo1Xnms783XGDze4rJQpu5WkRmUz7wletoG5LgnIldA3tPYpYkcci7bAHirGUZQlorO0nZjtkP3Fh+VBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad1c19f7095dfe811993945853f5f4066b314943f2597af7efef818a6a20f1f","last_reissued_at":"2026-07-05T10:31:42.175294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:42.175294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PathM3: A Multimodal Multi-Task Multiple Instance Learning Framework for Whole Slide Image Classification and Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hehuan Ma, Junzhou Huang, Michael Xiao, Qifeng Zhou, Wenliang Zhong, Yuzhi Guo","submitted_at":"2024-03-13T21:19:12Z","abstract_excerpt":"In the field of computational histopathology, both whole slide images (WSIs) and diagnostic captions provide valuable insights for making diagnostic decisions. However, aligning WSIs with diagnostic captions presents a significant challenge. This difficulty arises from two main factors: 1) Gigapixel WSIs are unsuitable for direct input into deep learning models, and the redundancy and correlation among the patches demand more attention; and 2) Authentic WSI diagnostic captions are extremely limited, making it difficult to train an effective model. To overcome these obstacles, we present PathM3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08967","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.08967/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.08967","created_at":"2026-07-05T10:31:42.175369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08967v2","created_at":"2026-07-05T10:31:42.175369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08967","created_at":"2026-07-05T10:31:42.175369+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLI4DH3QSXP6","created_at":"2026-07-05T10:31:42.175369+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLI4DH3QSXP6QEMZ","created_at":"2026-07-05T10:31:42.175369+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLI4DH3Q","created_at":"2026-07-05T10:31:42.175369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07006","citing_title":"GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB","json":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB.json","graph_json":"https://pith.science/api/pith-number/ZLI4DH3QSXP6QEMZHFCYKP27IB/graph.json","events_json":"https://pith.science/api/pith-number/ZLI4DH3QSXP6QEMZHFCYKP27IB/events.json","paper":"https://pith.science/paper/ZLI4DH3Q"},"agent_actions":{"view_html":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB","download_json":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB.json","view_paper":"https://pith.science/paper/ZLI4DH3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08967&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLI4DH3QSXP6QEMZHFCYKP27IB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLI4DH3QSXP6QEMZHFCYKP27IB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB/action/storage_attestation","attest_author":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB/action/author_attestation","sign_citation":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB/action/citation_signature","submit_replication":"https://pith.science/pith/ZLI4DH3QSXP6QEMZHFCYKP27IB/action/replication_record"}},"created_at":"2026-07-05T10:31:42.175369+00:00","updated_at":"2026-07-05T10:31:42.175369+00:00"}